Prediction of machining characteristics of Abrasive Water Jet Machined Al7075-TiB2 In-situ composite
| Autor: | Ramaiah Keshavamurthy, G.S. Pradeep Kumar, G. Ugrasen, S. Manjoth, J.T. Kavya |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
010302 applied physics
Materials science Traverse Abrasive Mechanical engineering 02 engineering and technology 021001 nanoscience & nanotechnology 01 natural sciences Volumetric flow rate Taguchi methods Machining 0103 physical sciences Surface roughness Feedforward neural network Orthogonal array 0210 nano-technology |
| Zdroj: | Materials Today: Proceedings. 24:851-858 |
| ISSN: | 2214-7853 |
| DOI: | 10.1016/j.matpr.2020.04.395 |
| Popis: | The current study emphasizes on predicting the characteristics of Abrasive Water Jet Machining of Al 7075-TiB2 In-situ composite. Experimental trials were carried out in accordance with Taguchi’s L25 orthogonal array. Feed forward type of Artificial Neural Network has been employed to develop the algorithm to estimate the machining characteristics such as volumetric material removal rate, surface roughness and dimensional error for the given traverse speed, abrasive flow rate and stand-off distance. A comparison study has been done to evaluate the deviation of predicted values from the experimental values. Back propagation feed forward neural network employed for building as well as training the network. It can be evident that utilization of 70% of data for network training yields very good prediction results and correlation of predicted responses with measured values |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect